All the models will have token limits, especially if you’re not paying for API access. You would have to tune a model based on the blog posts, but that’s expensive, degrades model quality, and isn’t easy to do.

Another thing you could do is have a model index the posts and then retrieve data based on search. The easiest way to do this would be download all the blog posts into a folder, then install cursor.com and open it on the folder. Cursor is for coding, but it will index your folder and then you can ask the model questions. You should be able to get this far with the free trial, but if you have a huge number of blog posts, it still won’t work

It will start hallucinating if you overfeed it

You know Wayland will be ready when these threads don’t get 100 comments

it’s just that software isn’t there yet.

I put about 2000 hours of work into $open_source_project. After a huge release 10xing the quality, we had about 1000x as many users.

The existing user base was ecstatic- for many of them, it was all they ever wanted and more. But we had 1000x new people saying “it just isn’t there yet”

Yea so this is why I support third parties. Dems need to be better than “not fascist”

I hear people say this, but how do we get it?

Or like, they want a built-in ad blocker and Tor support in a privacy respecting browser, as explained in the article

Ok but like, that makes a terrible default for Zorin OS users. They’re gonna be confused and think it’s some hot garbage

Not sure why they don’t just ship Firefox with extensions like uBlock pre-installed

Edit: it looks like they’re heavily tweaking Brave regardless. I doubt this move was for technical reasons

Chromium is more secure, so if you add privacy tweaks, it is arguably better: https://madaidans-insecurities.github.io/firefox-chromium.html#jit-hardening

(Btw I use Firefox)

Doesn’t Librewolf log you out of every site when you close it, by default? I don’t think that’s a good default

This is the correct way to do it. Even when I was hiring, I much preferred opening Quick Apply positions. I don’t want to waste your time either (and I sure as hell am not reading cover letters)

I mean how many jobs have you applied to online? I think about 1 in 100 applications leading to an interview is around standard, although some people will get lucky.

Also the reason we don’t explain why you didn’t get the job is because given hundreds of applications, that would take hours to do (I personally only look at a resume for 10+ seconds anyways) and we don’t want to open ourselves to legal retaliation

Unfortunately, it may be a good idea to “customize” each submission by incorporating keywords from the actual listing into your resume.

This is usually a bad idea, since quantity > quality for most people trying to get a professional job. But I do agree with the rest of your comment

1. I report any email that is spam as spam, so my inbox is quite clean and I don’t miss anything
2. I applied to ~600 positions, averaging about 100 positions an hour. You just have to be faster with the application process; don’t customize your resume, don’t read the job description, just apply

Fellow Canadian working in the US. Just be yourself they’re curious about you and your ideas

House of cards season 1 was…

Oh

I would watch a YouTube series doing this

It finally happened!?!

Came to the comments hoping someone deciphered the bottom text